{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"d2dce2612f16","filters":{"venue":"Statisctics and computing/Statistics and computing"}},"results":[{"id":"W982522955","doi":"10.1007/978-1-4614-9020-3_8","title":"Programming in R","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Analysis with R","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Programming language; Computer science; Programming paradigm; Order (exchange); Programming domain; C programming language; Object-oriented programming; Inductive programming; Artificial intelligence; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.01385810052166029,"gpt":0.2451940253181226,"spread":0.2313359247964624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005027733,0.0006644272,0.000901841,0.0004308245,0.0003674149,0.001273937,0.0007145357,0.0002396311,0.00002514324],"category_scores_gemma":[0.00006041024,0.0006864188,0.00006466689,0.000168835,0.0002206395,0.000204905,0.001626044,0.0008038849,0.00003051768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004949653,"about_ca_system_score_gemma":0.0001138586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048313,"about_ca_topic_score_gemma":0.0000452781,"domain_scores_codex":[0.9964592,0.00006236446,0.001041907,0.001229263,0.0004961339,0.0007111087],"domain_scores_gemma":[0.9974537,0.0007153373,0.000705044,0.0006653416,0.0001749291,0.0002856339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001234099,0.00001559891,0.0001476535,0.0001044119,0.00005516647,0.00008708463,0.0003976401,0.00005926005,9.394652e-7,0.542779,0.0007297952,0.4556222],"study_design_scores_gemma":[0.0005977418,0.000201681,0.00115051,0.0005814822,0.00009451387,0.0001140723,0.00007197584,0.816619,0.000001479691,0.1511187,0.02831689,0.001131931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003569327,0.00123422,0.9750584,0.0001610469,0.0003575903,0.000445492,0.00009209826,0.0001408187,0.02215337],"genre_scores_gemma":[0.04505215,0.0005251796,0.9389243,0.0003994329,0.000242345,0.000004481535,0.0001780773,0.0001155535,0.01455854],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8165597,"threshold_uncertainty_score":0.9997628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385489859","doi":"10.1007/978-3-031-33390-3_10","title":"Random Forests","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Sample (material); Mathematics; Statistics; Tree (set theory); Bootstrap aggregating; Artificial intelligence; Machine learning; Computer science; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.09674985517006617,"gpt":0.3869100027923107,"spread":0.2901601476222446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000770305,0.0008168565,0.001346649,0.0002079329,0.0006655976,0.0002742984,0.0002206796,0.0003431367,0.00003133702],"category_scores_gemma":[0.0007082761,0.0007983036,0.0001057073,0.00007111007,0.000394133,0.00004642471,0.0006712225,0.0008859384,0.00001297104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003331096,"about_ca_system_score_gemma":0.00008219956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001166343,"about_ca_topic_score_gemma":0.00003252848,"domain_scores_codex":[0.9964479,0.00009285982,0.001181123,0.001025106,0.0005201455,0.0007328244],"domain_scores_gemma":[0.9903677,0.007840212,0.0007666192,0.0004188638,0.0002254186,0.0003812476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002955355,0.00001587328,0.00001879954,0.0004949964,0.0001402612,0.0001339508,0.0003398273,0.0000884437,0.000001460875,0.7834142,0.001933793,0.2133888],"study_design_scores_gemma":[0.001020146,0.0001822347,0.0000932091,0.0005773483,0.0002665427,0.00006346618,0.000059473,0.1645309,0.0000012705,0.8290375,0.00340965,0.0007582576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000149689,0.000420556,0.9725197,0.00007143657,0.0006065919,0.0005436101,0.0009560912,0.0002439494,0.02448838],"genre_scores_gemma":[0.006478589,0.000733903,0.934991,0.0001509436,0.0004660309,0.000004348235,0.0001434859,0.000333352,0.05669833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2126306,"threshold_uncertainty_score":0.9994468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486382","doi":"10.1007/978-3-031-33390-3_12","title":"Support Vector Machines","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Hyperplane; Support vector machine; Mathematics; Real line; Separable space; Space (punctuation); Quadratic equation; Line (geometry); Kernel (algebra); Class (philosophy); Artificial intelligence; Combinatorics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01799468312861486,"gpt":0.2646509473033243,"spread":0.2466562641747095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003015983,0.0005305767,0.0005760159,0.0002371499,0.0007466553,0.0005967568,0.0004857864,0.0002284684,0.00002238604],"category_scores_gemma":[0.00002711251,0.0005547054,0.0000767111,0.0001317165,0.0001896886,0.00007777404,0.001116998,0.0005798369,0.00003806375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002681873,"about_ca_system_score_gemma":0.0000936881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002768881,"about_ca_topic_score_gemma":0.000009514732,"domain_scores_codex":[0.997498,0.00002753553,0.0007175413,0.0009503675,0.0003483872,0.0004581934],"domain_scores_gemma":[0.9979802,0.0005504941,0.0005418473,0.0005231243,0.0001631159,0.0002411857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000141473,0.000008628353,0.00002180978,0.00007831078,0.00004345274,0.00003527965,0.0001839961,0.00001748935,0.000004648055,0.7302947,0.002788967,0.2665213],"study_design_scores_gemma":[0.0003222796,0.0003649164,0.0008542939,0.0002040833,0.0000906701,0.0001898129,0.00002681487,0.5306683,0.00001259514,0.421241,0.04497031,0.001055004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007011134,0.0001912413,0.9699002,0.0002895586,0.0004517817,0.0003206216,0.0002608592,0.0006299353,0.02788571],"genre_scores_gemma":[0.05329677,0.001480702,0.8056377,0.0008314126,0.0007628397,0.00001290535,0.0002684543,0.0002794473,0.1374298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5306507,"threshold_uncertainty_score":0.9996905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486542","doi":"10.1007/978-3-031-33390-3_4","title":"Logistic Regression","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Logistic regression; Statistics; Covariate; Mathematics; Logistic model tree; Econometrics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1867757406559741,"gpt":0.4257310844756461,"spread":0.238955343819672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006736891,0.0008399514,0.001244128,0.000209724,0.0007086067,0.0002474652,0.0002245436,0.0003787086,0.00003509836],"category_scores_gemma":[0.0008598135,0.000769089,0.00008800284,0.00007390435,0.0004605915,0.00004216286,0.0007751414,0.0009788752,0.00001481595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004081078,"about_ca_system_score_gemma":0.00008169367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078875,"about_ca_topic_score_gemma":0.000008573063,"domain_scores_codex":[0.9964315,0.00009728759,0.001141181,0.001091699,0.0005323663,0.0007059994],"domain_scores_gemma":[0.99141,0.006676469,0.0008573393,0.0004545656,0.0002264526,0.0003752352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001478426,0.00001644262,0.000007569464,0.0005516771,0.00008944549,0.0001679569,0.0002674232,0.00003904387,0.000003281526,0.7613648,0.002199465,0.2352781],"study_design_scores_gemma":[0.0004312706,0.0002097929,0.00005141471,0.001025369,0.0002519147,0.00006917016,0.00008069524,0.1321086,0.000001678656,0.8615634,0.003431928,0.0007747336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009223673,0.0004858872,0.9714871,0.0000804744,0.0006687435,0.0004207333,0.0009058809,0.0002607313,0.02559819],"genre_scores_gemma":[0.005311747,0.0009903903,0.9264638,0.0001523172,0.0004226751,0.00000294043,0.0001488296,0.0002994202,0.06620785],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2345034,"threshold_uncertainty_score":0.999476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486861","doi":"10.1007/978-3-031-33390-3_9","title":"Trees","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Decision tree; Mathematics; Rectangle; Combinatorics; Boosting (machine learning); Artificial intelligence; Computer science; Discrete mathematics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02492851284539378,"gpt":0.2649124460204725,"spread":0.2399839331750788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003477581,0.0005361688,0.0005982905,0.0002181431,0.0007381117,0.0009112275,0.0006243691,0.0001939323,0.000007506433],"category_scores_gemma":[0.00004230448,0.0005612192,0.00005669983,0.0001270314,0.000218969,0.00009885351,0.001515425,0.0005505089,0.00004116965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002098645,"about_ca_system_score_gemma":0.00009599813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000299045,"about_ca_topic_score_gemma":0.00001507889,"domain_scores_codex":[0.9973259,0.00002690474,0.0006873847,0.001059075,0.0003906138,0.00051013],"domain_scores_gemma":[0.9975677,0.0009165742,0.0004869966,0.0006238688,0.0001404263,0.0002645099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.981859e-7,0.000007871007,0.0000109401,0.00004944283,0.00004669833,0.00003707028,0.0002833433,0.00002774956,0.000001294838,0.5985931,0.002836582,0.3981052],"study_design_scores_gemma":[0.0002962503,0.0001463439,0.0005890079,0.0002906395,0.00007017812,0.00008319545,0.00005185477,0.7181413,0.000001612403,0.2495574,0.03003574,0.0007364582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006393295,0.0004740593,0.9737697,0.0002882362,0.000533008,0.0002356124,0.0006136127,0.0003587661,0.02366313],"genre_scores_gemma":[0.005892499,0.00128922,0.9227986,0.0003958884,0.0005234854,0.000004591738,0.000382711,0.0001687215,0.06854428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7181135,"threshold_uncertainty_score":0.9996839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385489627","doi":"10.1007/978-3-031-33390-3_14","title":"Neural Networks","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Backpropagation; Artificial neural network; Normalization (sociology); Regularization (linguistics); Gradient descent; Stochastic gradient descent; Computer science; Artificial intelligence; Feedforward neural network; Nonlinear system; Dropout (neural networks); Feed forward; Algorithm; Mathematics; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02097023155890035,"gpt":0.2522566464519125,"spread":0.2312864148930122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002752948,0.0006087798,0.0006462328,0.0001587306,0.0008498857,0.0008607137,0.0005853162,0.0002381459,0.000006467379],"category_scores_gemma":[0.00001906271,0.0006241549,0.00007773731,0.0001532982,0.0002184644,0.00008669605,0.001470107,0.0008403582,0.00001227409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001917371,"about_ca_system_score_gemma":0.00004480788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001532994,"about_ca_topic_score_gemma":0.000009877569,"domain_scores_codex":[0.9971266,0.00003886946,0.0007520165,0.001073962,0.0003554937,0.0006530964],"domain_scores_gemma":[0.9973712,0.001066033,0.0005482907,0.0005607014,0.0001413925,0.0003123837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001611457,0.000007173799,0.00002122708,0.00004637123,0.00004376137,0.00006062087,0.0001047896,0.003342601,6.964463e-7,0.6920589,0.002684439,0.3016278],"study_design_scores_gemma":[0.0002184883,0.0001084772,0.0002773324,0.000138157,0.00005091431,0.00008038136,0.00001215705,0.853788,3.307026e-7,0.1385861,0.0061489,0.0005907934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001239783,0.0008289673,0.9866088,0.0003835321,0.0008764549,0.0003341428,0.0001086253,0.0003673917,0.0103681],"genre_scores_gemma":[0.3155575,0.004974764,0.5645449,0.003072161,0.003385646,0.00001603448,0.0006006178,0.00063755,0.1072109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8504454,"threshold_uncertainty_score":0.999621,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385489676","doi":"10.1007/978-3-031-33390-3_3","title":"Statistical Learning: Practical Aspects","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Variance (accounting); Bayes' theorem; Computer science; Scaling; Artificial intelligence; Algorithm; Machine learning; Variable (mathematics); Statistical learning; Mathematics; Statistics; Data mining; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.03189300187760231,"gpt":0.318637779957082,"spread":0.2867447780794797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004284033,0.0006934593,0.001117288,0.0002613573,0.0005928104,0.0002961578,0.00009383178,0.0003953997,0.0001067831],"category_scores_gemma":[0.0005237364,0.0007024265,0.00008660384,0.00008963783,0.0004465335,0.00004249022,0.00044405,0.001762646,0.00008238055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004445708,"about_ca_system_score_gemma":0.0003170601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002926398,"about_ca_topic_score_gemma":0.00001561368,"domain_scores_codex":[0.9966742,0.00006311583,0.0008766262,0.0009936448,0.000676946,0.0007154776],"domain_scores_gemma":[0.9963412,0.002090276,0.0004877426,0.0003015801,0.0002445672,0.0005346687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006625087,0.00005918836,0.0005835607,0.0007050387,0.0003628279,0.001524865,0.0004688559,0.0000382787,0.000005949578,0.8689556,0.007249762,0.1199799],"study_design_scores_gemma":[0.00520101,0.004236575,0.01180705,0.002674406,0.002853773,0.002777093,0.001603803,0.3764357,0.000007782678,0.4725325,0.1166427,0.003227728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00256083,0.001274469,0.7314981,0.002052072,0.001180482,0.001334801,0.0007549517,0.0007452805,0.258599],"genre_scores_gemma":[0.2200472,0.00607249,0.482755,0.002238353,0.002155913,0.000007384758,0.002725933,0.001072559,0.2829251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3964231,"threshold_uncertainty_score":0.9995427,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385489604","doi":"10.1007/978-3-031-33390-3_1","title":"Prologue","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Economic Theory and Institutions","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Prologue; Computer science; Mathematics; Art; Literature","retraction":null,"screen_n_in":null,"score":{"opus":0.03725975681368367,"gpt":0.227419429981194,"spread":0.1901596731675103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005700504,0.0004765277,0.0008726309,0.0002856321,0.0006625765,0.0002917926,0.0002072011,0.0002914438,0.00009933546],"category_scores_gemma":[0.00008606796,0.0005912277,0.00008180154,0.00005474937,0.0003832811,0.00007072955,0.0004385827,0.0006074688,0.0002546903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004037254,"about_ca_system_score_gemma":0.00004674571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003499189,"about_ca_topic_score_gemma":0.00001708504,"domain_scores_codex":[0.9974627,0.00001490481,0.001118827,0.0008793272,0.00005174663,0.0004724169],"domain_scores_gemma":[0.9981077,0.0004777769,0.0008412803,0.0003274787,0.00005117041,0.0001945515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006506442,0.00001319347,0.0002871615,0.0001451493,0.0001419054,0.00003282769,0.000410595,0.0001439264,3.014572e-7,0.9743692,0.001594011,0.02285528],"study_design_scores_gemma":[0.0004066273,0.0001420492,0.0006971995,0.0001616773,0.00004437513,0.00004622387,0.00006007325,0.06107602,5.089011e-7,0.8665894,0.07008418,0.0006916544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002650787,0.003817474,0.4071855,0.0004206249,0.002764146,0.0007394776,0.005650466,0.0003531655,0.5764183],"genre_scores_gemma":[0.4633685,0.006681335,0.1056878,0.00172072,0.002174756,0.0000135691,0.001450937,0.0006602106,0.4182421],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4607177,"threshold_uncertainty_score":0.9996539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486397","doi":"10.1007/978-3-031-33390-3_7","title":"Nearest Neighbors","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"k-nearest neighbors algorithm; Computer science; Pattern recognition (psychology); Naive Bayes classifier; Artificial intelligence; Classifier (UML); Similarity (geometry); Data mining; Machine learning; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.02556425250823703,"gpt":0.2586592445469714,"spread":0.2330949920387343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003087306,0.0005771513,0.0006153883,0.0003324968,0.0006868925,0.001028232,0.0007096131,0.0003000728,0.00001221028],"category_scores_gemma":[0.00008629457,0.0005932801,0.00006340119,0.00015507,0.0003334614,0.0001244661,0.001656316,0.0006746995,0.00004816905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003267646,"about_ca_system_score_gemma":0.0001039436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001724143,"about_ca_topic_score_gemma":0.000008170062,"domain_scores_codex":[0.9971855,0.00003124934,0.0007507852,0.001036391,0.0004475188,0.0005485864],"domain_scores_gemma":[0.9974222,0.0009356362,0.0006281477,0.0006521308,0.0001574595,0.0002044927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000152893,0.000007363566,0.00005782878,0.00007603842,0.00004649634,0.00004674835,0.0002444739,0.00002794883,0.000002180024,0.6954619,0.002507172,0.3015203],"study_design_scores_gemma":[0.0004195845,0.0002279044,0.001258429,0.0002973815,0.00006478435,0.00005799504,0.0001180633,0.3503798,0.000007082328,0.6159829,0.03021773,0.0009683255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001437864,0.0006982122,0.9655215,0.0006881821,0.0008577871,0.0003042899,0.0001561294,0.000974073,0.03065602],"genre_scores_gemma":[0.1274056,0.003923284,0.7139563,0.0009102091,0.0006346993,0.000008475196,0.0003146095,0.0003530463,0.1524938],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3503518,"threshold_uncertainty_score":0.9996518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W58877873","doi":"10.1007/978-1-4614-9020-3_4","title":"Importing, Exporting and Producing Data","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.124470994372565,"gpt":0.3666736128907216,"spread":0.2422026185181566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001464133,0.0008355008,0.001274013,0.0001615922,0.0007528146,0.0006578895,0.0003914308,0.0002967586,0.0001075929],"category_scores_gemma":[0.002000491,0.0008040202,0.00004083753,0.00005918193,0.0004614666,0.000101673,0.002190262,0.0009894093,0.000005587731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002460326,"about_ca_system_score_gemma":0.0001157521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007382182,"about_ca_topic_score_gemma":0.00001210117,"domain_scores_codex":[0.9953117,0.00009824005,0.001760799,0.001597147,0.0004904777,0.0007416584],"domain_scores_gemma":[0.9925093,0.00416325,0.00174208,0.0009120903,0.0002678965,0.0004053656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004726077,0.00001677621,0.0002611869,0.0007158879,0.0001047598,0.00004738375,0.0006284792,0.000001587813,0.000007316057,0.6102278,0.002451631,0.3855324],"study_design_scores_gemma":[0.0004358271,0.0002158326,0.0009082509,0.001162801,0.0003550475,0.0001905454,0.0002275481,0.2260032,0.000003752368,0.7661672,0.003268126,0.001061886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006368903,0.00195178,0.9576004,0.0001356488,0.0005544721,0.0008967528,0.001064293,0.0001915776,0.03123625],"genre_scores_gemma":[0.0258316,0.0005962772,0.9641643,0.0001930793,0.0005470192,0.000002746694,0.0002027909,0.0001974456,0.008264769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3844706,"threshold_uncertainty_score":0.9994411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4252485560","doi":"10.1007/978-1-4614-9020-3_1","title":"Introducing R","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"clone (Java method); Programming language; Computer science; Software; Window (computing); Code (set theory); Statistical software; Statistical analysis; Software engineering; Computer graphics (images); Mathematics; Operating system; Statistics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01125833925195088,"gpt":0.2346782035492136,"spread":0.2234198642972627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005042443,0.0007662112,0.000983391,0.0003458363,0.0006947212,0.001592664,0.0008457921,0.0002452873,0.00006409719],"category_scores_gemma":[0.00008761522,0.0007766703,0.00008334391,0.0001278799,0.0002619803,0.000227741,0.002190995,0.0008318527,0.00007121275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004513716,"about_ca_system_score_gemma":0.000122365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006276633,"about_ca_topic_score_gemma":0.00001032353,"domain_scores_codex":[0.9961247,0.00006520678,0.001031922,0.001500487,0.0005792312,0.0006984772],"domain_scores_gemma":[0.9966124,0.0008696775,0.0008776719,0.0009764629,0.0002914469,0.0003723148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001317882,0.00001061301,0.00003406226,0.000108441,0.0001315563,0.00004927629,0.0003731493,0.0001297687,0.000003754058,0.6530789,0.005837354,0.3402418],"study_design_scores_gemma":[0.0003923654,0.0001759343,0.0003003741,0.0003357579,0.0001710806,0.0001470757,0.0000436093,0.7915807,0.00000378247,0.1769177,0.02886415,0.001067521],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001429077,0.001232489,0.961753,0.0002706278,0.0006174967,0.0002913915,0.0001604887,0.0001827907,0.03534882],"genre_scores_gemma":[0.0191096,0.0006917922,0.9460507,0.0007270572,0.0006698564,0.000002149108,0.0002274393,0.00013596,0.03238544],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7914509,"threshold_uncertainty_score":0.9994684,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486431","doi":"10.1007/978-3-031-33390-3_2","title":"Statistical Learning: Concepts","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Statistical learning; Bayes' theorem; Interpretation (philosophy); Variance (accounting); Naive Bayes classifier; Supervised learning; Unsupervised learning; Statistics; Mathematics; Bayesian probability; Artificial neural network; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.102508996654528,"gpt":0.4155633201201151,"spread":0.313054323465587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008343753,0.0009561243,0.001482038,0.0002110327,0.0008610063,0.0003305329,0.0002374157,0.0004244039,0.00008804355],"category_scores_gemma":[0.001307972,0.0009731741,0.00008958358,0.00008155072,0.0007163296,0.00005213181,0.0007760911,0.001582428,0.00002604769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004836718,"about_ca_system_score_gemma":0.0001185929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000137327,"about_ca_topic_score_gemma":0.000009421668,"domain_scores_codex":[0.9956103,0.0001781955,0.001349645,0.001289625,0.0006648327,0.0009074109],"domain_scores_gemma":[0.9869798,0.01098137,0.0008472834,0.0003834619,0.0002768052,0.0005313054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001942714,0.0000207391,0.00002337657,0.0004968438,0.0001443128,0.0002055409,0.0004680432,0.0000836235,0.000002762865,0.7811038,0.002108273,0.2153232],"study_design_scores_gemma":[0.0006135841,0.0003831162,0.0001001028,0.0004943619,0.0003011529,0.00007973389,0.0001727467,0.1382968,0.000001405115,0.8488599,0.009724691,0.0009724165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001329079,0.0003359977,0.9646716,0.00006961573,0.0005593973,0.0004762573,0.001297964,0.0003378774,0.03211845],"genre_scores_gemma":[0.009417924,0.0008071822,0.9111578,0.0001523398,0.0004461999,0.00000426512,0.0002941306,0.0003806193,0.07733954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2143508,"threshold_uncertainty_score":0.9992719,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486326","doi":"10.1007/978-3-031-33390-3_13","title":"Feature Engineering","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Artificial intelligence; Logarithm; Data mining; Machine learning; Mathematics; Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01220526921624156,"gpt":0.2435632484900194,"spread":0.2313579792737778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000216097,0.0004669385,0.0004650192,0.0001030257,0.0002629851,0.0001452376,0.0001665682,0.0004678934,0.000004644479],"category_scores_gemma":[0.0001315577,0.0004696767,0.00006091475,0.00004056761,0.0002188845,0.000001569312,0.0005818211,0.0005075865,0.000006392142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008844573,"about_ca_system_score_gemma":0.00006009693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005166633,"about_ca_topic_score_gemma":0.000006327385,"domain_scores_codex":[0.9983175,0.00001819847,0.0003353862,0.0006863347,0.0002189878,0.0004235847],"domain_scores_gemma":[0.9989843,0.0002372373,0.000242925,0.0002564819,0.00008513236,0.0001939555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004085829,0.00002501139,0.0002598132,0.0007712983,0.000593904,0.000216459,0.0003905509,0.000344927,0.000515927,0.2564201,0.04257757,0.6978436],"study_design_scores_gemma":[0.00200519,0.001754379,0.00318329,0.001622949,0.0004885485,0.0004994876,0.0003159649,0.1838454,0.0001325795,0.03243713,0.7703181,0.003396991],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00993752,0.01303517,0.9416732,0.001165963,0.003455621,0.0008609622,0.001943325,0.0005887027,0.02733949],"genre_scores_gemma":[0.09352043,0.007632566,0.5617148,0.001148705,0.003953899,0.000007426389,0.002685944,0.0007788347,0.3285574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7277405,"threshold_uncertainty_score":0.9997755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385486392","doi":"10.1007/978-3-031-33390-3_11","title":"Boosting","year":2023,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Multinomial logistic regression; Artificial intelligence; Computer science; Machine learning; AdaBoost; Random forest; Mathematics; Classifier (UML)","retraction":null,"screen_n_in":null,"score":{"opus":0.03486239759677846,"gpt":0.2658821743200783,"spread":0.2310197767232999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005451122,0.0006858439,0.0007548344,0.0002555424,0.0008120132,0.001009828,0.0006006699,0.0002969482,0.000007199894],"category_scores_gemma":[0.00008832846,0.0007338351,0.00007224514,0.0001222794,0.0002241397,0.0001077514,0.001546764,0.0009084301,0.00003699692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002895926,"about_ca_system_score_gemma":0.0001506191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002842381,"about_ca_topic_score_gemma":0.000007574866,"domain_scores_codex":[0.9966611,0.0000500097,0.0008822267,0.001205294,0.0004975571,0.000703853],"domain_scores_gemma":[0.9971252,0.001167829,0.0006066288,0.0005351715,0.0002259632,0.0003391738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001793378,0.00000660789,0.00002038056,0.0001307006,0.00005597986,0.00009681535,0.0004530204,0.0001697375,0.000003175478,0.7006793,0.0009598143,0.2974227],"study_design_scores_gemma":[0.0002326849,0.000141325,0.0001383767,0.0005034335,0.0000548468,0.00009705179,0.00003246329,0.6431707,0.000002175844,0.3524867,0.002428323,0.0007119161],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001170605,0.0007091512,0.9632402,0.0002062574,0.0007911596,0.000205294,0.0001308378,0.0004571654,0.03414287],"genre_scores_gemma":[0.08974124,0.001619088,0.8383316,0.0009117764,0.0007908524,0.000003119191,0.0001557028,0.0002946731,0.068152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.643001,"threshold_uncertainty_score":0.9995112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}